Agentic AI › Authority
Limits & Oversight
The limits that are not the agent's own, and what broke them.
In Agentic AI → Authority · 2 screens
RecordsGuardrailsThe limits that are not the agent's own. Checked before every tool call and again against what it would move. A new deployment with agents and no limits is one bad prompt away from a thousand purchase orders.OpenRecordsIncidentsA guardrail broken, a loop caught, a cost overrun, an unsupported claim. Separate from the run because a breach outlives it: it is the thing somebody reviews on Monday.Open
Columns, fields and actions
| Screen | Kind | What it is | Columns | Fields | Actions |
|---|---|---|---|---|---|
| Guardrails | List | The limits that are not the agent's own. Checked before every tool call and again against what it would move. A new deployment with agents and no limits is one bad prompt away from a thousand purchase orders. | 14 | 21 | 0 |
| Incidents | List | A guardrail broken, a loop caught, a cost overrun, an unsupported claim. Separate from the run because a breach outlives it: it is the thing somebody reviews on Monday. | 11 | 3 | 0 |